Simple removal test on own image

[guist]

Hello,

I would like to test your model of shadow removal on a random image but I am a bit confused where to save the image as well as which command to type in.

For now, I saved the image under datasets/test/, but when I run

python test.py --dataset_root ../datasets/

I get the following error:

AssertionError: ../datasets/test/input is not a valid directory

If I create an input directory, then the program is asking me for a target directory and a maskdirectory. Both should contain the same number of elements as the input directory.

But if I test on a random image, I do not have any target or mask, so I do not know how to proceed. Could you please help me?

Thanks!
Guillaume

[naoto0804]

Hi! Unfortunately, the server I use is under emergency maintenance (and it seems to be severe), I cannot push the codes.

The easiest workaround will be as follows:

1. put shadow detection results in <PRECOMP_MASK_NAME> (Note that SP+M model assumes access to a pre-computed mask in addition to the input image. You may try some shadow detection models to get it.)
2. put a symbolic link as below. Images in each folder might be loaded but do not affect the test process, I hope.

- datasets
  - <DATASET_NAME>
    - test
      - input
      - target (symlink to input)
      - mask (symlink to input)
      - <PRECOMP_MASK_NAME>

3. try python test.py --dataset_root ../datasets/<DATASET_NAME> --name <IDENTIFIER> --mask_to_G <PRECOMP_MASK_NAME> --mask_to_G_thresh 0.95

[naoto0804]

I have uploaded the codes. You can use --dataset_mode demo for a case we only have access to only input images. For more details, please refer to #3. If it is not working, please feel free to let me know.